Improving Recognition Performance in Multiple Enrollment Based Fingerprint Recognition Systems

Abstract

Multiple enrollment based fingerprint recognition systems have for long been known for good recognition accuracies. They however suffer poor matching speeds, a lot of memory consumption and the recognition accuracies are still very low; making implementation in real-world applications difficult. This paper presents a novel approach that performs prior selection of good fingerprint image samples of an individual for matching to further improve recognition performance, reduce the matching speed as well as memory consumption. A spectral minutiae based matching method and two fingerprint databases (FVC2000-DB2 and FVC2006-DB2) were used. A comparison of our results with the existing ones presented in literature shows that they are more superior. This makes it possible to design better multiple enrollment based fingerprint recognition systems with a high recognition accuracy, high matching speed and low memory consumption using our approach.